Three Papers at ICASSP 2026: From Missing Samples to Personalized 3D Audio

Excited to share that our team has three papers at ICASSP 2026! Together, these works explore new ways to recover richer speech, create more immersive spatial audio, and move toward personalized HRTF estimation directly from 3D geometry.

• “Sampling-Rate-Agnostic Speech Super-Resolution Based on Gaussian Process Dynamical Systems with Deep Kernel Learning,” Aditya Arie Nugraha, Diego Di Carlo, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii.

• “SIRUP: A Diffusion-Based Virtual Upmixer of Steering Vectors for Highly-Directive Spatialization with First-Order Ambisonics,” Emilio Picard, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii.

• “Physics-Informed Learning of Neural Scattering Fields Towards Measurement-Free Mesh-to-HRTF Estimation,” Tancrède Martinez, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii.

Many thanks to all collaborators!